DeepMind’s AI Trained For 5 Years... But Why?

แชร์
ฝัง
  • เผยแพร่เมื่อ 24 ธ.ค. 2024

ความคิดเห็น • 863

  • @TEMPLERTV
    @TEMPLERTV ปีที่แล้ว +966

    A few years ago you helped ignite my passion of machine learning. Since then I’ve learned to code, have educated myself vastly in machine learning. I’m currently building my own small NN. Thanks for opening my eyes to something amazing

    • @TwoMinutePapers
      @TwoMinutePapers  ปีที่แล้ว +116

      That is absolutely amazing, so happy to hear your story! Hope the neural network will go on to do great things!

    • @HiddenExp
      @HiddenExp ปีที่แล้ว +19

      @@TwoMinutePapers You are big my fellow scholar

    • @bubbleboy821
      @bubbleboy821 ปีที่แล้ว +3

      The first time I learned about them was SethBling'd Mario NN

    • @Litwinel
      @Litwinel ปีที่แล้ว +3

      @@TwoMinutePapers this must be a great feeling to know you are an inspiration for others

    • @electron6825
      @electron6825 ปีที่แล้ว +2

      @@ThatGuy-kz3fx neural nutwork

  • @Makmarian
    @Makmarian ปีที่แล้ว +1794

    It would be cool if there were simulated sport competitions where teams used their own AI model against each other

    • @raylopez99
      @raylopez99 ปีที่แล้ว +193

      They do this already with chess, computer chess competitions, the latest winner is AlphaZero-based Leela, just beat the reigning champ StockFish.

    • @SpaghettiToaster
      @SpaghettiToaster ปีที่แล้ว +24

      @@raylopez99 Didn't Stockfish win?

    • @TwoMinutePapers
      @TwoMinutePapers  ปีที่แล้ว +227

      Loving the idea.

    • @cosmos3576
      @cosmos3576 ปีที่แล้ว +32

      I would like to see this also in FIFA.

    • @sebastianjost
      @sebastianjost ปีที่แล้ว +18

      There are competitions like that. Not sure if there are any for sports, but I've definitely heard of some other competitions:
      - Minecraft village/ city generation AIs
      - Minecraft resource gathering AIs (get diamonds etc.)
      - Ticket to ride AIs (board game)
      - bad piggies/ angry birds AIs (not sure which one)
      - chess AIs
      ...this is what I remember without actively looking for them. If you look for competitions like that, I'm sure you'll find some.

  • @anthonybernstein1626
    @anthonybernstein1626 ปีที่แล้ว +1010

    To get a feeling of how difficult this is: imagine QWOP with 56 keys instead of 4, and you don't just have to run but to play football, in 3D instead of 2.

    • @dzambi
      @dzambi ปีที่แล้ว +172

      @eetm but your 🧠 is just a processor playing 3d qwop in the dark.

    • @InceyWincey
      @InceyWincey ปีที่แล้ว +64

      To get a feeling of how difficult this is, try to consciously control all of the muscles that are required to walk.
      Or just appreciate the fact that your brain can do that for you while you think about more important things.

    • @sfurules
      @sfurules ปีที่แล้ว +42

      @@dzambi I didn't expect this level of existential crisis on a chill Sunday....

    • @jamqdlaty
      @jamqdlaty ปีที่แล้ว +28

      Also the buttons are pressure sensitive. ;)

    • @spizzleyo
      @spizzleyo ปีที่แล้ว +2

      All things should be related to QWOP

  • @miladragon
    @miladragon ปีที่แล้ว +318

    I notice that they still seem to move really unnaturally -- their upper bodies seem very flail-y. I wonder if that would get ironed out if they were given some cost to excess movement (just like humans get tired).

    • @Saotik
      @Saotik ปีที่แล้ว +68

      I was just typing something similar before I saw your post. I even used the word "flaily". Adding fatigue to the simulation feels like it might have significant impact.

    • @budnick1
      @budnick1 ปีที่แล้ว +57

      Along similar lines, if there was some cost to getting hit, like being slow to move for some time, I wonder if there would be an emergent consensus to avoid causing damage to your opponent, like an emergent moral code. Would they even develop a tit-for-tat rule enforcement?

    • @nemonomen3340
      @nemonomen3340 ปีที่แล้ว +13

      I was also about to say this. It seems to be a commonly overlooked issue when training AIs in movement.

    • @maelstrom2313
      @maelstrom2313 ปีที่แล้ว +18

      They may be moving more efficiently than real football players. People don't always take the most efficient paths when moving, we have to consider extraneous social variables of how our movement looks. It's possible that it takes more energy to restrict the movement of limbs than to incorporate their inertia into the body's trajectory.

    • @miladragon
      @miladragon ปีที่แล้ว +25

      @@maelstrom2313 if that were the case, real soccer players would move like this. No one cares about looking stupid if they win (cf. the Fosbury flop, which looks stupid but is standard, because it lets you jump higher). There's also no reason to think that these should be moving efficiently, because there's no incentive for them to be doing so (they don't get tired).

  • @jordyp3696
    @jordyp3696 ปีที่แล้ว +310

    they should do this with real rules (throw ins and cornershots etc), and with 11v11, run it for weeks on different computers, see if they come up with some kind of great strategy, see what formation and stuff they pick.

    • @letMeSayThatInIrish
      @letMeSayThatInIrish ปีที่แล้ว +118

      And add stamina so they have to learn to economize their energy.

    • @softwarelivre2389
      @softwarelivre2389 ปีที่แล้ว +57

      And goalkeepers

    • @alihms
      @alihms ปีที่แล้ว +69

      And a referee.. who always seems to be one sided too for the real effect.

    • @Кабанчик-х7м
      @Кабанчик-х7м ปีที่แล้ว +17

      @@letMeSayThatInIrish yeah... genetic, height, weight, heart illness, traumas :D

    • @nobodyishere
      @nobodyishere ปีที่แล้ว +4

      @@alihms lmao

  • @818suki
    @818suki ปีที่แล้ว +65

    Even after all these years, you still amaze me with how understandable you make these papers for people like me. Thanks for really spending time in digesting this information to someone who's not in the field or can't allocate enough time to dive deep.

    • @TwoMinutePapers
      @TwoMinutePapers  ปีที่แล้ว +5

      You are too kind - thank you so much! 🙏

  • @SP-ny1fk
    @SP-ny1fk ปีที่แล้ว +229

    Imagine training an AI to do a task for 100 years in 10 minutes, then exporting it and importing it into a robot to achieve the task perfectly in the real world
    What a time to be alive!

    • @spinninglink
      @spinninglink ปีที่แล้ว +4

      Think i saw something about them doing that with a ping pong machine, right?

    • @CircuitrinosOfficial
      @CircuitrinosOfficial ปีที่แล้ว +8

      I wonder if they inject noise into the simulation to simulate the imperfections of reality.

    • @derekofbaltimore
      @derekofbaltimore ปีที่แล้ว +4

      Your point holds but i dont think that doing things in simulated world corresponds 1 to 1 with the real world. It would still need lots of training in real world (because the simulated world wouldn't hold all the variables that the real world holds and those small inconsistencies add up)

    • @josesandv
      @josesandv ปีที่แล้ว +5

      I have always ponder that if our universe is simulated, maybe it is in a supercomputer that does million of iterations, where every iteration takes milliseconds but for us is eternity

    • @el2746
      @el2746 ปีที่แล้ว

      @@josesandv More like every millisecond does millions of iterations

  • @Quazlyy
    @Quazlyy ปีที่แล้ว +183

    I think the pre-training behaviour pretty much captures the behaviour of actual football players

    • @vasekbrezina2801
      @vasekbrezina2801 ปีที่แล้ว +2

      Exactly :-)

    • @brooksgunn5235
      @brooksgunn5235 ปีที่แล้ว +3

      I was gonna say 😂

    • @theinacircleoftheancientpu492
      @theinacircleoftheancientpu492 ปีที่แล้ว

      Ah, the bugs kick in sometimes.

    • @v1kzu
      @v1kzu ปีที่แล้ว +6

      From the expert opinion of someone who's never watched football before

    • @JH-ji6cj
      @JH-ji6cj ปีที่แล้ว +2

      @Vixan knowing football, but not acknowledging flopping from a foul? Who doesn't watch football?: you

  • @jhunt5578
    @jhunt5578 ปีที่แล้ว +67

    It's crazy how the AI just iterates and comes up with through passes, lobs and cruyff turns.

    • @jakab174
      @jakab174 ปีที่แล้ว +3

      i am a little bit sceptical, with this, there are probably thousands of hours of footage and they show the best most human like stuff, these are things that just comes from the noise. If the ai would be any good they would shoot the ball directly to the empty net every time, then it would learn its better to put one player to the goal

    • @yousuck6222
      @yousuck6222 ปีที่แล้ว

      @@DailyCorvid You dont need a ref with robots. That's the point.

  • @rogueyun9613
    @rogueyun9613 ปีที่แล้ว +218

    Honestly the first one where all the players are writhing on the ground looks pretty accurate to me.

    • @KangJangkrik
      @KangJangkrik ปีที่แล้ว +1

      Seizure?

    • @KuZiMeiChuan
      @KuZiMeiChuan ปีที่แล้ว +4

      @@KangJangkrik The other team hit me.

    • @dranirbanpal
      @dranirbanpal ปีที่แล้ว +7

      Yes, that's advanced training on what to do after a foul

    • @vibovitold
      @vibovitold ปีที่แล้ว +3

      neymaring the shit out of the game

    • @Soupie62
      @Soupie62 ปีที่แล้ว

      If that was truly all you need do to play, I might stand a chance of qualifying.

  • @monocore
    @monocore ปีที่แล้ว +56

    I see some serious meme potential in this

    • @FenrizNNN
      @FenrizNNN ปีที่แล้ว +7

      We can make a religion out of this

    • @MarcillaSmith
      @MarcillaSmith ปีที่แล้ว +2

      What is the game the AI is playing? It looks like non Americans trying to invent their own version of football 🏈

    • @LinggarMaretvaCendani
      @LinggarMaretvaCendani ปีที่แล้ว +4

      @@MarcillaSmith Why do you call it football when you bring the ball using hands? Shouldn't it called Handball?

    • @speedfastman
      @speedfastman ปีที่แล้ว +4

      @@LinggarMaretvaCendani No it should be called soccer cuz it socs.

    • @MarcillaSmith
      @MarcillaSmith ปีที่แล้ว

      @@LinggarMaretvaCendani handball is when you can't afford a racquetball racquet.

  • @JakeHaugen
    @JakeHaugen ปีที่แล้ว +105

    This actually could be a really cool esports team. Like imagine if madden had AI agents to play the team. It was actually pretty entertaining to watch.

    • @michaelatorn8380
      @michaelatorn8380 ปีที่แล้ว +13

      I see great potential in deadly sport types played by AI.

    • @zapdart1803
      @zapdart1803 ปีที่แล้ว +2

      Worth checking out altered state machine and their upcoming games (FIFA AI League and AIFA)

    • @Ulexcool
      @Ulexcool ปีที่แล้ว

      Nah

    • @MrUbister
      @MrUbister ปีที่แล้ว +3

      @@Ulexcool Hater

    • @brendanrodgers9753
      @brendanrodgers9753 ปีที่แล้ว +1

      @@michaelatorn8380 any examples of what sports specifically, can't think of any other than extreme diving

  • @manofsan
    @manofsan ปีที่แล้ว +11

    *Imagine a Zombie movie/show where the zombies first start out writhing on the ground, and then quickly they learn to get up and walk, and then run, etc, etc*

    • @vibovitold
      @vibovitold ปีที่แล้ว

      and once the movie credits start rolling, there's Pink Floyd's classic playng in the background
      "...Hey, teacher! leave them kids alone..."

    • @thecousindeci1103
      @thecousindeci1103 ปีที่แล้ว +2

      bruh thats a really cool idea for a game. The longer you live the smarter the zombies get with ai, honestly it would be scary as shit when they all learn to run and look for you in houses. Something like project zomboid but at some point the zombies learn to coordinate.

  • @MasterReset7
    @MasterReset7 ปีที่แล้ว +3

    You voice are a IA too? o.O

  • @chrisfaulkner9355
    @chrisfaulkner9355 ปีที่แล้ว +1

    The way this dude pauses to extend EVERY diphthong. A-and. So-O. No-O. YE-es.

  • @DudeWatIsThis
    @DudeWatIsThis ปีที่แล้ว +1

    8:22 **gets lightly tripped over, falls down and has pain seizures**
    The most realisting thing in the entire video.

  • @BryceRogers
    @BryceRogers ปีที่แล้ว +25

    It would be cool to watch the 50 days AI vs the 3 days just to really show the improvement.

  • @zodiepupper
    @zodiepupper ปีที่แล้ว +45

    I would absolutely watch videos of a bunch of ai players fumble around like this for hours.

    • @devfromthefuture506
      @devfromthefuture506 ปีที่แล้ว +1

      Me too and I would like to ask where I can find more videos of these

    • @zapdart1803
      @zapdart1803 ปีที่แล้ว +2

      FIFA AI League is releasing in less than a month. You will get your wish

    • @aaronconnolly1496
      @aaronconnolly1496 ปีที่แล้ว

      Just go outside man

  • @volkan7505
    @volkan7505 ปีที่แล้ว +2

    The talking sound so robot like. Its like you have all the words with your voice already recorded and then you just type the words which automatically creates the voice

  • @surajvkothari
    @surajvkothari ปีที่แล้ว +11

    If this simulation gets more accurate, it could influence how football is played in real life. Imagine when the richest clubs can afford to create such simulations and optimise their players.

    • @bobisatelier
      @bobisatelier ปีที่แล้ว

      they wouldn't need to be rich probably

  • @otto-pi8xu
    @otto-pi8xu ปีที่แล้ว +1

    I need this to become a thing, like using real football matches to train the AI and have simulated matches between real teams based on how they play. I would love that.

  • @xAgentVFX
    @xAgentVFX ปีที่แล้ว +11

    I want more Ai Football!!! I wanna watch a full match! Looks so fun. Imagine what they might do years from now??

  • @usm1le
    @usm1le ปีที่แล้ว +3

    realistic human movement that follows the laws of gravity and moves on its own has always been fascinating to me

  • @revimfadli4666
    @revimfadli4666 ปีที่แล้ว +1

    7:32 AI really pulled a Blue Lock there💀

  • @ai_is_a_great_place
    @ai_is_a_great_place ปีที่แล้ว +1

    I can't wait to see the Olympic AI Opening ceremony!

  • @JanBadertscher
    @JanBadertscher ปีที่แล้ว +9

    I would love to find out with a model like this what the ideal play style would be according to game theory and physical limits of the players, but still having to follow all the rules. For example: Would it actually be better even for the goal keeper to move out and play in the field, vs. staying in the goal? I guess humans didn't figure out optimal gameplay yet for soccer and this could lead to new and crazy strategies.

    • @SweBeach2023
      @SweBeach2023 ปีที่แล้ว +1

      It was my initial thought as well. Using AI we could try so many new strategies. And it wouldn't be hard to give the different AI players different properties to reflect the properties of the real players of a professional team. On eis a faster runner, another have better stamina, a third one have great control of the ball etc.

  • @REDSIDEofficial
    @REDSIDEofficial ปีที่แล้ว

    Wow! The first steps of a Simulation World just started, can’t wait to see virtual peoples doing tasks like our own.

  • @galenorla8066
    @galenorla8066 ปีที่แล้ว +14

    0:57 looks like a real football game to me...
    4:22 Has a promising career ahead.

  • @OperationDarkside
    @OperationDarkside ปีที่แล้ว +2

    Boston Dynamics vs Real Madrid when?
    Also I want to see 100 vs 100 players and if this can be transferred onto soldiers like in Totally Accurate Battle Simulator.

  • @tim40gabby25
    @tim40gabby25 ปีที่แล้ว +1

    Remarkable. Ex footy player here, wondering how long till these analyses show how Messi's additional value was in the distribution of labour - a 'team player'.

  • @ianbot
    @ianbot ปีที่แล้ว +6

    How epic is it gonna be when a fellow scholar makes a soccer game like FIFA but using these AI's

    • @zapdart1803
      @zapdart1803 ปีที่แล้ว

      FIFA AI League game is about to be released on the App Store

  • @Player-ix7rx
    @Player-ix7rx ปีที่แล้ว +1

    Ok, now put the code into 22 boston dynamics robots and let's go

  • @abhishtagatya
    @abhishtagatya ปีที่แล้ว +2

    on multi-agent ai, do we have to relearn a strategy for 11 v 11 instead of the current 2 v 2? i assume so because in theory its a different game?

  • @petermoras6893
    @petermoras6893 ปีที่แล้ว +3

    I think one of the major improvements in the last few years we've seen in AI training (besides training size/time) is how we train intermediate goals to speed up training.
    If we simply took the untrained AI with the joint body, and asked them to learn soccer, it would take forever with minimal improvement.
    But as we've seen in this video, they first train the AI to enable it to walk, dribble, and kick the soccer ball.
    Once the AI knows how to perform general ball handling tasks, it can use that understanding to more quickly learn to score goals.
    This might just be my perception though.

    • @vibovitold
      @vibovitold ปีที่แล้ว +1

      the next logical step would be (and it's probably already done to some extent, in one way or another) to split the AI into a "teacher" (supervisory) and a "pupil" (learning) AI, whereby the former one would be in charge of figuring out and setting the incremental goals for the latter to accomplish

  • @lGNITED
    @lGNITED ปีที่แล้ว +2

    Two Minute Papers, thank you so much for providing us such incredible content.

  • @dillanio9191
    @dillanio9191 ปีที่แล้ว +1

    They're using their body to shield the ball and then turning around to beat the pressure from opponent... Wow.. That's something one of the best midfielders of all time Xavi did often too... Incredible

  • @sithmaster
    @sithmaster ปีที่แล้ว +6

    Just imagine the labour curve going down suddenly after a couple of weeks… nobody knowing why… and AI looks like it would start to discuss and talk to each other on the field rather than playing. THAT would give me goosebumps. ;D
    What a time to be here.

  • @ariseyhun2085
    @ariseyhun2085 ปีที่แล้ว +6

    I'm quite curious why many of the graphs have staggers going down, instead of continuously improving. Any idea what that might be about? For example, in "Passing Range" it goes down inthe 1 week range at 6:35

    • @coder0xff
      @coder0xff ปีที่แล้ว +8

      It's complicated because you're working with many variables. Imagine you're going to your friends house but you don't have a map of the roads, just a compass that points to your friends house. You go down a road that gets you closer, but it's a dead end. You have to go back the way you came a little to find the better road that will get you even closer.
      If we imagine that hip angle is the x axis of a map, and ankle angle is the y axis, then we might settle into an effective ankle angle. But then hey, if we tweak the hip angle a bit we can get even better, but the ankle angle needs to be adjusted again. It's like this, but with way more variables.

    • @ariseyhun2085
      @ariseyhun2085 ปีที่แล้ว +1

      @@coder0xff thank you so much for this explanation!

  • @larryking6259
    @larryking6259 ปีที่แล้ว

    Thank you especially for comments on those graphs. Big respect!

  • @markaron9356
    @markaron9356 ปีที่แล้ว +2

    *DeepMind - Magical Skills, Goals & Assists - 2023 | HD*

  • @drawmaster77
    @drawmaster77 ปีที่แล้ว +3

    it would be interesting if they added some stamina function, so they run more realistically and not swings their limbs all over the place.

    • @ChristopherCricketWallace
      @ChristopherCricketWallace ปีที่แล้ว

      yeah. I would like to see the rules built-in, as well. Let the AI learn in the context of the real game with out of bounds, and penalties, corner kicks, etc.

    • @drawmaster77
      @drawmaster77 ปีที่แล้ว

      @@ChristopherCricketWallace I mean this maybe overdoing it with the rules, but at least have them run more realistically not like they are spazzing out with limbs flailing all over the place lol. Maybe add some cost to limb movement which factors into their stamina bar and when stamina is low they run really slow which would affect their performance and that way AI would learn to be more "efficient".
      Just throwing some thoughts out there.

  • @mason4295
    @mason4295 ปีที่แล้ว

    2:11 "Holy mother of papers!!" hahahaha love it. Great videos and papers 🤖

  • @Enceos
    @Enceos ปีที่แล้ว +2

    I wonder if it's possible to train certain skills first, like getting up, sprinting and kicking separately, then continue with the game training.

  • @jaybrandon557
    @jaybrandon557 8 หลายเดือนก่อน

    This is the kind of niche thing that I personally really enjoy reading in my own time, but it's so much better when you have a PhD holder narrating for you and showing you all of the nuance that you might have missed.

  • @bradleyandrews2444
    @bradleyandrews2444 ปีที่แล้ว

    these little foot ball player are so fun to watch i could watch that for the whole day

  • @TheChipMcDonald
    @TheChipMcDonald ปีที่แล้ว +1

    They're training them on rotoscoped humans playing, so was the feints with the footwork introducing "noise" that was creating the initial shaking/quivering? When they're running they take lots of tiny steps, which makes me think that's a latent trait of the human data set foot-faking distorting the training?

  • @GikePeterson
    @GikePeterson ปีที่แล้ว

    2:20 We used to do the same trick when we were kids, passing over the wall when we played soccer.

  • @SMASH_REVIEWS
    @SMASH_REVIEWS ปีที่แล้ว +2

    HOLY MOTHER of Papers,... Hahaha
    Love u Man.

  • @kairu_b
    @kairu_b ปีที่แล้ว +1

    I like your storytelling, sir. What a time to be alive!

  • @flamingosoup6375
    @flamingosoup6375 ปีที่แล้ว +1

    I wish there was like a place I could go and watch these AI do their thing in real-time, I could watch that stuff for hours.

  • @thomasrosebrough9062
    @thomasrosebrough9062 ปีที่แล้ว +1

    0:53 me when mom says I can't have another pack of fruit gushers until I eat some broccoli

  • @hunterjohnson6513
    @hunterjohnson6513 ปีที่แล้ว

    And to think how jaw dropping it was to see open AI dominating a 1v1 against pros in Dota 2 years ago. Unreal how far it’s come and it’s only going to grow exponentially from here

  • @Plumfan_
    @Plumfan_ ปีที่แล้ว +3

    It would be awesome if they can also simulate some form of fatigue, some movements look too energetic or wasteful.

  • @argo2720
    @argo2720 ปีที่แล้ว

    it would be so sick to see full teams progress and having a goalie learning how to goalie and adding in rules like offsides, out, fouls, penalties. would like to see what formations they would come up with or if they would stick with the all forward all back game plan

  • @ServerAcademy
    @ServerAcademy ปีที่แล้ว

    How do you train AI like this with UE or Unity? I dont understand how that works and I coulnd't find any tutorials on it but Im not sure what to look for..

  • @awesomeniac
    @awesomeniac ปีที่แล้ว

    That red AI trying to feint injury crack me up

  • @heck-r
    @heck-r ปีที่แล้ว

    As far as I I understood what I saw, they weren't really passing.
    It was more like a combination of
    0) Run towards the ball
    1) Shoot as close to the goal as possible while avoiding the enemy (including bouncing off of the wall)
    2) If teammate has the ball then position towards the middle and the goal (essentially where teammate will shoot), which is indeed impressive
    It may not sound like there is a difference, but there is, because passing to a teammate so he can shoot at the empty net is not the same as shooting the ball next to the enemy, missing the goal, and hope teammate gets there (who gets there, because he expects the missed shot)

  • @khangvinh4656
    @khangvinh4656 ปีที่แล้ว +1

    1:13 This is proof that not knowing how to play football can cause extreme cases of seizures.

  • @Me-ic3li
    @Me-ic3li ปีที่แล้ว

    Excited for the day one of them picks the ball up and invents rugby

  • @PsychBoost
    @PsychBoost ปีที่แล้ว

    I hope you have seen "Lawyer Explains Stable Diffusion Lawsuit (Major Implications!)" by corridor crew uploaded a few hours ago. He even uses your catchphrase at the end! What a time to be alive!

  • @theflashevo6137
    @theflashevo6137 ปีที่แล้ว +2

    Wow, this video showcases the impressive capabilities of DeepMind's AI technology. The ability for the AI to learn and adapt to the complex rules and strategies of football in a simulated environment is truly mind-blowing. I can't wait to see how this technology will be applied in the real world and the impact it will have on the future of sports and beyond.

  • @AdekunleAdeniranThe1st
    @AdekunleAdeniranThe1st 5 หลายเดือนก่อน +1

    Bro got nutmeged💀 0:27

  • @ianbot
    @ianbot ปีที่แล้ว +1

    I'd like to see a self-driving car trained in this way:
    We just need to use input data of some data of cars driving perfectly (at intersections, changing lanes, parking) and we can make a simulation where an AI agent is given the ability to press the gas pedal, steer left, right, use turn signals, (etc.) and also given input data about the car's position in lane, positions of nearby cars and pedestrians. We already have the technology to gather this data from cameras (tesla).
    Then we would train the AI agents. And if they can control these soccer players that have at least 20 different joint controls that need such fine tuning, we should be able to train an agent to drive a car, even have races, do tricks, or just drive from point A to B without crashing.

  • @emeca33_amulatoaztek
    @emeca33_amulatoaztek ปีที่แล้ว

    i love your content bruh, long time fan! ölelés!

  • @adlwilliams
    @adlwilliams ปีที่แล้ว

    The fact that it learned to embellish an injury, only to pop right back up is great

  • @Plafintarr
    @Plafintarr ปีที่แล้ว +7

    My heart desires a whole tournament with these little AI's. Crazy ragdoll physics and wild flailing bodyparts included. They are so fun to watch! Can you upload more footage?

  • @BigBaibars
    @BigBaibars ปีที่แล้ว +1

    This guy was an opera singer in his previous life

  • @Walter5850
    @Walter5850 ปีที่แล้ว +1

    AI scientists should have a competition to see whose model can train their players better and have an actual virtual football cup.

  • @woodybob01
    @woodybob01 ปีที่แล้ว +5

    One day there's gonna be a better way to 'start' these training projects. It just seems wrong that they should start with such little knowledge. I'm sure something will arise as we work towards the future.
    By the way this was damn impressive! Just the mere fact that it could side-step and through-ball shows how much of an understanding it really has about the game, a surprisingly deep one!

    • @bingchiIIing
      @bingchiIIing ปีที่แล้ว +1

      @@DailyCorvid loving this

  • @visualbree
    @visualbree ปีที่แล้ว

    The through ball at 4:29 is amazing 🔥🔥

  • @martiddy
    @martiddy ปีที่แล้ว +2

    5:15 It seems that it was trained with Neymar footage haha

  • @Bzorlan
    @Bzorlan ปีที่แล้ว +2

    If 11 a side and the full rules of the game were added then this could eventually be used to discover new tactics. Similar to how the chess ai developed its own strategies that humans could never think of.

  • @MrCZRC
    @MrCZRC ปีที่แล้ว

    Some reason this amazes me more than chatgpt. Absolutely love watching A.I grow and learn how to play games

  • @NielsMacLean
    @NielsMacLean ปีที่แล้ว

    how powerful of a processing unit did they train for those 5 days of drill training?

  • @mjpunited5727
    @mjpunited5727 ปีที่แล้ว +2

    Physics agents are so interesting, I wonder if there is any demo of this that I can find so I can run it myself. Would love to train goalkeepers and play 6v6 or even branch out to something like fencing!

  • @jameshomer2949
    @jameshomer2949 หลายเดือนก่อน

    Apparently they used 3 phases. Imitate motion capture. drills, and actual matches. It would be interesting to develop and optimize training program (max level reach in less training time) and apply same approach to humans, predicting when they would be able to reach professional levels, and evaluating their current performance and how much they need to train to reach pro level

  • @ali_dogu
    @ali_dogu ปีที่แล้ว

    Ayo very cool video! But why does the "Division of Labour" Chart start so high? They didn't Teamplay in the beginning, did they?

  • @pandoraeeris7860
    @pandoraeeris7860 ปีที่แล้ว +4

    I, for one, welcome our new AI football overlords.

  • @cmilkau
    @cmilkau ปีที่แล้ว

    3:03 What's the colour coding showing? I don't know football that well

  • @MACHINEBUILDER
    @MACHINEBUILDER ปีที่แล้ว +8

    Just imagine if this ai was put into a robot and you had to play soccer against it. It'd be horrifying with how they move - imagine if they even looked like people 💀
    Still absolutely insane progress with this kind of physics-based ai agents! It's crazy!

    • @asrar4907
      @asrar4907 ปีที่แล้ว +4

      you do remember the part where he said that the ai trained without a refree? Gosh you need an ambulance

    • @davidwuhrer6704
      @davidwuhrer6704 ปีที่แล้ว

      RoboCup Humanoid League

    • @MACHINEBUILDER
      @MACHINEBUILDER ปีที่แล้ว

      @@asrar4907 Ahha yeah you'd definitely need at least an ambulance after playing against these

    • @dagdbot83
      @dagdbot83 ปีที่แล้ว

      I think they did that already

  • @chikita5110
    @chikita5110 ปีที่แล้ว +1

    I studied multiagents theory at university and I can't wait to see this expermient go with more players !
    BTW if anyone has sources about theory of agents interactions in tthis context

  • @PaulGaither
    @PaulGaither ปีที่แล้ว

    As a sports fan, it would be great to see 11 on 11 at a larger scale, add the rules of the game, and factor in variables such as height, weight, strength, speed, endurance, etc.

  • @wihatmi5510
    @wihatmi5510 ปีที่แล้ว

    To make it more realistic the ai should no only know which movements are possible but also in which position how much force the body can create and also how fast the whole body or certain parts of it get tired and take all this into account. Also they should have a field of vision with moving eyes that can only focus on a certain point directly and just aprroximate the rest and not know what the others thinks but predicting it from their action. After that it might look exactly like real soccer. Maybe it's possible to use it in a video game. The player just selects who they want to control and points in the direction and shoots and everything else is done by the AI.

  • @jaikumar848
    @jaikumar848 ปีที่แล้ว +2

    Will any football club like barcelona use it to develop new strategies?

  • @coder0xff
    @coder0xff ปีที่แล้ว +10

    The tantrum after being knocked over is really interesting. It doesn't seem to be the optimal playing strategy, and I doubt the AI had its feelings hurt. Why doesn't it get up and get back to the game?

    • @ayoCC
      @ayoCC ปีที่แล้ว

      Downtime was the most optimal play maybe lmao

    • @ACED1
      @ACED1 ปีที่แล้ว +5

      probably just like bugs (the insect), it doesn't know how to. it didn't ever learn how to properly get up, because only goals are rewarded. that's the main focus

  • @qhieu195
    @qhieu195 ปีที่แล้ว

    Reinforcement learning 2022 trend: get a lot of data and through it into GPUs training with visualization -> obviously get something look eye-catching

  • @funnycompilations8314
    @funnycompilations8314 ปีที่แล้ว +2

    Now that the video mentions pre-training and training time, I was wondering: is the human brain so good at few shot learning because it has already been pre-trained over thousands if not millions of years? So when a new baby is born, the brain of that baby only needs to be fine tuned to the environment. I'm asking these questions because very often I hear people saying that our methods are inefficient because it takes like 1 month and 10 thousand GPUs to train these models and our brain can do it way more efficiently. But as I said previously, I do think training the human brain wasn't more efficient either as the brain itself needed millions of brains and thousands of years to pre-train itself (evolution basically). Let me know your thoughts.

    • @martiddy
      @martiddy ปีที่แล้ว

      That's true, there are some behaviors that humans and also many animals do instinctively without previous knowledge, mainly because our brain are preprogrammed already by evolution for certain things that improves how fast we adapt to our environment.

    • @vibovitold
      @vibovitold ปีที่แล้ว

      various parts of our brains are already wired for specific tasks (eg. spatial recognition, speech recognition; there are specific centers in the brain, of course they sill need to be fed data to get up and running correctly, but they're already set up for performing specific types of learning and stimuli processing).
      so we're getting a lot "for free" - courtesy of millions of years of evolution - in our hardware layer, so to speak

  • @Glowbox3D
    @Glowbox3D ปีที่แล้ว

    One of my favorite 'agent' training examples. So wild.

  • @petercooper8317
    @petercooper8317 ปีที่แล้ว

    If someone makes TMP out of context, “one second passes in exactly one second” would definitely be in it

  • @Felixxenon
    @Felixxenon ปีที่แล้ว +1

    I imagine a.i agents will optimize sports tactics and train real players in the (near) future

  • @jaikumar848
    @jaikumar848 ปีที่แล้ว +1

    Hello sir ! I want to know how good is general purpose AI against specialist AI ? Is general purpose AI is like "Jack of all trade and master of none " against specialist A.I ?

    • @coder0xff
      @coder0xff ปีที่แล้ว +2

      There aren't currently any general purpose AIs, but it seems reasonable that a specialist AI would be able to do certain things better than AI general AI. It's not really a "specialist" otherwise.

  • @Quran_moha-c1d
    @Quran_moha-c1d ปีที่แล้ว +2

    1:00 the footballers like babies he crying

  • @TheBartalamey
    @TheBartalamey ปีที่แล้ว +1

    Watching all this physics simulations and last Boston Dynamics video about Atlas and all the struggles they get, i'm interested when BD will use machine learning instead of direct behavioral coding?

    • @NigraXXL
      @NigraXXL ปีที่แล้ว

      I'm pretty sure they already do. They have a simulation they use to train stuff, then make adjustments if the output doesn't work in real life

  • @pearhat640
    @pearhat640 ปีที่แล้ว

    this channel is so underrated. Also its quite scary

  • @parthasarathyvenkatadri
    @parthasarathyvenkatadri ปีที่แล้ว +1

    How long before we watch
    world cup AI

  • @crazytiger6
    @crazytiger6 ปีที่แล้ว

    The corner of the internet where blue lines make us make happy noises if my favorite corner of the internet

  • @tnadymacek
    @tnadymacek ปีที่แล้ว

    Pure gold, they play like half of my classmates on PE :D

  • @MrHeliMan
    @MrHeliMan ปีที่แล้ว

    I always wanted a physics-based walking system in a videogame and although I never thought I'll be here for it, this makes me think I just might.
    Counter-Strike 2 where you have to be careful about how fast you're running down the stairs or walking on mud?
    Yes, please.

  • @arifdiansdocumentary
    @arifdiansdocumentary ปีที่แล้ว

    0:56: "How much beer do you need"
    Him: "Yes"

  • @ahabkapitany
    @ahabkapitany ปีที่แล้ว

    "5 years pass by in 3 days. Are you thinking what I'm thinking?"
    Well I'm thinking about that Black Mirror episode with a clenched stomach...